1 files changed, 107 insertions, 75 deletions

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 0748e7ea5210..e4af6616e1df 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -118,8 +118,6 @@
 #include <linux/btf_ids.h>
 #include <linux/bpf-cgroup.h>
 
-#include "scm.h"
-
 static atomic_long_t unix_nr_socks;
 static struct hlist_head bsd_socket_buckets[UNIX_HASH_SIZE / 2];
 static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2];
@@ -548,7 +546,7 @@ static void unix_write_space(struct sock *sk)
 		if (skwq_has_sleeper(wq))
 			wake_up_interruptible_sync_poll(&wq->wait,
 				EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND);
-		sk_wake_async(sk, SOCK_WAKE_SPACE, POLL_OUT);
+		sk_wake_async_rcu(sk, SOCK_WAKE_SPACE, POLL_OUT);
 	}
 	rcu_read_unlock();
 }
@@ -757,7 +755,7 @@ static int unix_bind(struct socket *, struct sockaddr *, int);
 static int unix_stream_connect(struct socket *, struct sockaddr *,
 			       int addr_len, int flags);
 static int unix_socketpair(struct socket *, struct socket *);
-static int unix_accept(struct socket *, struct socket *, int, bool);
+static int unix_accept(struct socket *, struct socket *, struct proto_accept_arg *arg);
 static int unix_getname(struct socket *, struct sockaddr *, int);
 static __poll_t unix_poll(struct file *, struct socket *, poll_table *);
 static __poll_t unix_dgram_poll(struct file *, struct socket *,
@@ -980,12 +978,12 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern,
 	sk->sk_write_space	= unix_write_space;
 	sk->sk_max_ack_backlog	= net->unx.sysctl_max_dgram_qlen;
 	sk->sk_destruct		= unix_sock_destructor;
-	u	  = unix_sk(sk);
+	u = unix_sk(sk);
+	u->listener = NULL;
+	u->vertex = NULL;
 	u->path.dentry = NULL;
 	u->path.mnt = NULL;
 	spin_lock_init(&u->lock);
-	atomic_long_set(&u->inflight, 0);
-	INIT_LIST_HEAD(&u->link);
 	mutex_init(&u->iolock); /* single task reading lock */
 	mutex_init(&u->bindlock); /* single task binding lock */
 	init_waitqueue_head(&u->peer_wait);
@@ -1599,6 +1597,7 @@ restart:
 	newsk->sk_type		= sk->sk_type;
 	init_peercred(newsk);
 	newu = unix_sk(newsk);
+	newu->listener = other;
 	RCU_INIT_POINTER(newsk->sk_wq, &newu->peer_wq);
 	otheru = unix_sk(other);
 
@@ -1690,19 +1689,18 @@ static void unix_sock_inherit_flags(const struct socket *old,
 		set_bit(SOCK_PASSSEC, &new->flags);
 }
 
-static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
-		       bool kern)
+static int unix_accept(struct socket *sock, struct socket *newsock,
+		       struct proto_accept_arg *arg)
 {
 	struct sock *sk = sock->sk;
-	struct sock *tsk;
 	struct sk_buff *skb;
-	int err;
+	struct sock *tsk;
 
-	err = -EOPNOTSUPP;
+	arg->err = -EOPNOTSUPP;
 	if (sock->type != SOCK_STREAM && sock->type != SOCK_SEQPACKET)
 		goto out;
 
-	err = -EINVAL;
+	arg->err = -EINVAL;
 	if (sk->sk_state != TCP_LISTEN)
 		goto out;
 
@@ -1710,12 +1708,12 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
 	 * so that no locks are necessary.
 	 */
 
-	skb = skb_recv_datagram(sk, (flags & O_NONBLOCK) ? MSG_DONTWAIT : 0,
-				&err);
+	skb = skb_recv_datagram(sk, (arg->flags & O_NONBLOCK) ? MSG_DONTWAIT : 0,
+				&arg->err);
 	if (!skb) {
 		/* This means receive shutdown. */
-		if (err == 0)
-			err = -EINVAL;
+		if (arg->err == 0)
+			arg->err = -EINVAL;
 		goto out;
 	}
 
@@ -1725,6 +1723,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
 
 	/* attach accepted sock to socket */
 	unix_state_lock(tsk);
+	unix_update_edges(unix_sk(tsk));
 	newsock->state = SS_CONNECTED;
 	unix_sock_inherit_flags(sock, newsock);
 	sock_graft(tsk, newsock);
@@ -1732,7 +1731,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags,
 	return 0;
 
 out:
-	return err;
+	return arg->err;
 }
 
 
@@ -1775,51 +1774,60 @@ out:
 	return err;
 }
 
+/* The "user->unix_inflight" variable is protected by the garbage
+ * collection lock, and we just read it locklessly here. If you go
+ * over the limit, there might be a tiny race in actually noticing
+ * it across threads. Tough.
+ */
+static inline bool too_many_unix_fds(struct task_struct *p)
+{
+	struct user_struct *user = current_user();
+
+	if (unlikely(READ_ONCE(user->unix_inflight) > task_rlimit(p, RLIMIT_NOFILE)))
+		return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN);
+	return false;
+}
+
+static int unix_attach_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+	if (too_many_unix_fds(current))
+		return -ETOOMANYREFS;
+
+	UNIXCB(skb).fp = scm->fp;
+	scm->fp = NULL;
+
+	if (unix_prepare_fpl(UNIXCB(skb).fp))
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void unix_detach_fds(struct scm_cookie *scm, struct sk_buff *skb)
+{
+	scm->fp = UNIXCB(skb).fp;
+	UNIXCB(skb).fp = NULL;
+
+	unix_destroy_fpl(scm->fp);
+}
+
 static void unix_peek_fds(struct scm_cookie *scm, struct sk_buff *skb)
 {
 	scm->fp = scm_fp_dup(UNIXCB(skb).fp);
+}
 
-	/*
-	 * Garbage collection of unix sockets starts by selecting a set of
-	 * candidate sockets which have reference only from being in flight
-	 * (total_refs == inflight_refs).  This condition is checked once during
-	 * the candidate collection phase, and candidates are marked as such, so
-	 * that non-candidates can later be ignored.  While inflight_refs is
-	 * protected by unix_gc_lock, total_refs (file count) is not, hence this
-	 * is an instantaneous decision.
-	 *
-	 * Once a candidate, however, the socket must not be reinstalled into a
-	 * file descriptor while the garbage collection is in progress.
-	 *
-	 * If the above conditions are met, then the directed graph of
-	 * candidates (*) does not change while unix_gc_lock is held.
-	 *
-	 * Any operations that changes the file count through file descriptors
-	 * (dup, close, sendmsg) does not change the graph since candidates are
-	 * not installed in fds.
-	 *
-	 * Dequeing a candidate via recvmsg would install it into an fd, but
-	 * that takes unix_gc_lock to decrement the inflight count, so it's
-	 * serialized with garbage collection.
-	 *
-	 * MSG_PEEK is special in that it does not change the inflight count,
-	 * yet does install the socket into an fd.  The following lock/unlock
-	 * pair is to ensure serialization with garbage collection.  It must be
-	 * done between incrementing the file count and installing the file into
-	 * an fd.
-	 *
-	 * If garbage collection starts after the barrier provided by the
-	 * lock/unlock, then it will see the elevated refcount and not mark this
-	 * as a candidate.  If a garbage collection is already in progress
-	 * before the file count was incremented, then the lock/unlock pair will
-	 * ensure that garbage collection is finished before progressing to
-	 * installing the fd.
-	 *
-	 * (*) A -> B where B is on the queue of A or B is on the queue of C
-	 * which is on the queue of listening socket A.
-	 */
-	spin_lock(&unix_gc_lock);
-	spin_unlock(&unix_gc_lock);
+static void unix_destruct_scm(struct sk_buff *skb)
+{
+	struct scm_cookie scm;
+
+	memset(&scm, 0, sizeof(scm));
+	scm.pid  = UNIXCB(skb).pid;
+	if (UNIXCB(skb).fp)
+		unix_detach_fds(&scm, skb);
+
+	/* Alas, it calls VFS */
+	/* So fscking what? fput() had been SMP-safe since the last Summer */
+	scm_destroy(&scm);
+	sock_wfree(skb);
 }
 
 static int unix_scm_to_skb(struct scm_cookie *scm, struct sk_buff *skb, bool send_fds)
@@ -1878,8 +1886,10 @@ static void scm_stat_add(struct sock *sk, struct sk_buff *skb)
 	struct scm_fp_list *fp = UNIXCB(skb).fp;
 	struct unix_sock *u = unix_sk(sk);
 
-	if (unlikely(fp && fp->count))
+	if (unlikely(fp && fp->count)) {
 		atomic_add(fp->count, &u->scm_stat.nr_fds);
+		unix_add_edges(fp, u);
+	}
 }
 
 static void scm_stat_del(struct sock *sk, struct sk_buff *skb)
@@ -1887,8 +1897,10 @@ static void scm_stat_del(struct sock *sk, struct sk_buff *skb)
 	struct scm_fp_list *fp = UNIXCB(skb).fp;
 	struct unix_sock *u = unix_sk(sk);
 
-	if (unlikely(fp && fp->count))
+	if (unlikely(fp && fp->count)) {
 		atomic_sub(fp->count, &u->scm_stat.nr_fds);
+		unix_del_edges(fp);
+	}
 }
 
 /*
@@ -1908,11 +1920,12 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 	long timeo;
 	int err;
 
-	wait_for_unix_gc();
 	err = scm_send(sock, msg, &scm, false);
 	if (err < 0)
 		return err;
 
+	wait_for_unix_gc(scm.fp);
+
 	err = -EOPNOTSUPP;
 	if (msg->msg_flags&MSG_OOB)
 		goto out;
@@ -2157,13 +2170,15 @@ static int queue_oob(struct socket *sock, struct msghdr *msg, struct sock *other
 	maybe_add_creds(skb, sock, other);
 	skb_get(skb);
 
+	scm_stat_add(other, skb);
+
+	spin_lock(&other->sk_receive_queue.lock);
 	if (ousk->oob_skb)
 		consume_skb(ousk->oob_skb);
-
 	WRITE_ONCE(ousk->oob_skb, skb);
+	__skb_queue_tail(&other->sk_receive_queue, skb);
+	spin_unlock(&other->sk_receive_queue.lock);
 
-	scm_stat_add(other, skb);
-	skb_queue_tail(&other->sk_receive_queue, skb);
 	sk_send_sigurg(other);
 	unix_state_unlock(other);
 	other->sk_data_ready(other);
@@ -2184,11 +2199,12 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 	bool fds_sent = false;
 	int data_len;
 
-	wait_for_unix_gc();
 	err = scm_send(sock, msg, &scm, false);
 	if (err < 0)
 		return err;
 
+	wait_for_unix_gc(scm.fp);
+
 	err = -EOPNOTSUPP;
 	if (msg->msg_flags & MSG_OOB) {
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
@@ -2209,7 +2225,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 			goto out_err;
 	}
 
-	if (sk->sk_shutdown & SEND_SHUTDOWN)
+	if (READ_ONCE(sk->sk_shutdown) & SEND_SHUTDOWN)
 		goto pipe_err;
 
 	while (sent < len) {
@@ -2553,8 +2569,10 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 
 	mutex_lock(&u->iolock);
 	unix_state_lock(sk);
+	spin_lock(&sk->sk_receive_queue.lock);
 
 	if (sock_flag(sk, SOCK_URGINLINE) || !u->oob_skb) {
+		spin_unlock(&sk->sk_receive_queue.lock);
 		unix_state_unlock(sk);
 		mutex_unlock(&u->iolock);
 		return -EINVAL;
@@ -2566,6 +2584,8 @@ static int unix_stream_recv_urg(struct unix_stream_read_state *state)
 		WRITE_ONCE(u->oob_skb, NULL);
 	else
 		skb_get(oob_skb);
+
+	spin_unlock(&sk->sk_receive_queue.lock);
 	unix_state_unlock(sk);
 
 	chunk = state->recv_actor(oob_skb, 0, chunk, state);
@@ -2594,6 +2614,10 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 		consume_skb(skb);
 		skb = NULL;
 	} else {
+		struct sk_buff *unlinked_skb = NULL;
+
+		spin_lock(&sk->sk_receive_queue.lock);
+
 		if (skb == u->oob_skb) {
 			if (copied) {
 				skb = NULL;
@@ -2602,12 +2626,22 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
 					WRITE_ONCE(u->oob_skb, NULL);
 					consume_skb(skb);
 				}
-			} else if (!(flags & MSG_PEEK)) {
-				skb_unlink(skb, &sk->sk_receive_queue);
-				consume_skb(skb);
+			} else if (flags & MSG_PEEK) {
+				skb = NULL;
+			} else {
+				__skb_unlink(skb, &sk->sk_receive_queue);
+				WRITE_ONCE(u->oob_skb, NULL);
+				unlinked_skb = skb;
 				skb = skb_peek(&sk->sk_receive_queue);
 			}
 		}
+
+		spin_unlock(&sk->sk_receive_queue.lock);
+
+		if (unlinked_skb) {
+			WARN_ON_ONCE(skb_unref(unlinked_skb));
+			kfree_skb(unlinked_skb);
+		}
 	}
 	return skb;
 }
@@ -2678,18 +2712,16 @@ redo:
 		last = skb = skb_peek(&sk->sk_receive_queue);
 		last_len = last ? last->len : 0;
 
+again:
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
 		if (skb) {
 			skb = manage_oob(skb, sk, flags, copied);
-			if (!skb) {
+			if (!skb && copied) {
 				unix_state_unlock(sk);
-				if (copied)
-					break;
-				goto redo;
+				break;
 			}
 		}
 #endif
-again:
 		if (skb == NULL) {
 			if (copied >= target)
 				goto unlock;